A Method of Optimizing FPGA Resources Based on Timing Multiplexing

Abstract

The present invention relates to the field of electronic information technology, and specifically refers to a method for optimizing FPGA resources based on time series multiplexing. The method of the present invention is applied to the following processing systems, including a data collector and a processing module, and the data collector sets n-way data Acquisition also includes the acquisition and time slot distribution module arranged between the data collector and the processing module; the present invention utilizes the FPGA timing multiplexing method to make the multi-channel processing process share a set of circuits, and by collecting and time slot distribution, the FPGA's The processing clock is quadrupled to save resources. The advantages are: 1. Save resources; 2. Save time; 3. Support parallel and serial processing modes; 4. No need to occupy additional cache.

Description

technical field [0001] The invention relates to the technical field of electronic information, in particular to an FPGA resource optimization method based on timing multiplexing. Background technique [0002] A multi-channel parallel processing method based on FPGA, that is, a processing method for multiple data streams, taking four inputs as an example, describes a processing for multiple data streams, the input data timing and processing requirements are as follows : [0003] 1. Input data timing: The data streams a, b, c and d are clocked at double the clock rate, denoted by clk_1x, input data_1, data_2, data_3 and data_4 channels in parallel and continuously updated, as shown in the attached figure 1 As shown, that is, when the rising edge of each clock of clk_1x arrives, data_1, data_2, data_3, and data_4 all have new inputs; that is, channels a, b, c, and d all have new inputs; [0004] 2. Processing requirements: When the rising edge of each clock of clk_1x arrives,...

AI Technical Summary

Problems solved by technology

This method requires four identical computing modules, that is, computing resources consume four shares, but its simultaneous four-way processing takes the same time as single-way processing, so it is called parallel processing. The advantage is that it shortens the time compared to serial processing Four times the processing time, but consumes four times the computing resources

[0008] Both serial and parallel processing above require four identical computing modules, that is, computing resources consume four

Images